Researchers submit patent application, “Machine Learning Systems And Methods For Assessing Medical Interventions For Utilization Review,” for approval (USPTO 20220115135): Patent Application – InsuranceNewsNet

MAY 03, 2022 (NewsRx) — By a News Reporter – Staff News Editor at Daily Insurance News — Since washington d.c.NewsRx reporters report that a patent application from Lieberman inventor Daniel M. (Phoenix, ArizonaUnited States), filed on December 21, 2021was posted on April 14, 2022.

No assignee for this patent application has been named.

The news editors got the following quote from background information provided by the inventors: “Determining whether a particular medical invention is appropriate for a given patient continues to be difficult. Such determinations are important, however, because they can have a profound impact on patient health outcomes, health care costs, and other individual and societal factors.

“In the context of health insurance providers and other entities in similar situations, it is particularly desirable to avoid false positives, i.e. cases in which a patient is incorrectly classified as a candidate and/or subjected to unnecessary medical interventions. To this end, health insurance providers often conduct a “utilization review” in which the insurer assesses the medical necessity of a requested medical procedure for the purpose of providing prior authorization.

“Even given recent advances in medical care, insurance case management techniques and data analysis, healthcare costs (and therefore insurance premiums) continue to rise dramatically. unsustainable. This is partly due to the difficulty of determining whether a requested medical intervention is appropriate for a particular person in the circumstances.

“Therefore, systems and methods are needed that overcome the limitations of the prior art. Various features and characteristics will also be apparent from the subsequent detailed description and appended claims, taken in conjunction with the accompanying drawings and this background section. »

In addition to background information on this patent application, NewsRx correspondents also obtained the inventor’s summary information for this patent application: “Various embodiments of the present invention relate to systems and methods for, among other i) using machine learning techniques to determine whether a chosen medical intervention is necessary; ii) using heterogeneous forms of aggregated data (such as imaging, laboratory studies, test results, investigation information, etc.) as input to a machine learning system as described herein, ii) improving insurer usage reviews using the machine learning systems described herein; iii) use several pre-trained artificial neural networks to implement the machine learning systems described here; and iv) use the trainee systems automatic ssage described herein to determine if a particular health care provider or physician is appropriate given the desired medical intervention.

“Various other embodiments, aspects and features are described in more detail below.”

The claims provided by the inventors are:

“1. A machine learning system for determining the appropriateness of a selected medical intervention, the system comprising: a plurality of health data sources, the health data sources providing at least one health data file a first type, and a second data file of a second type; a normalization module configured to receive the first and second data files and perform a normalization procedure on at least one of the first and second data files data; and a previously trained machine learning model configured to receive the normalized data files and produce a prediction output, the prediction output including a level of confidence associated with an adequacy of the selected medical intervention.

2. A machine learning system according to claim 1, wherein the at least one machine learning model is an artificial neural network.

A machine learning system according to claim 1, wherein the at least one machine learning model is a probabilistic neural network.

4. A machine learning system according to claim 1, wherein the at least one machine learning model is a convolutional neural network.

5. A machine learning system according to claim 1, wherein the at least one machine learning model is a decision tree.

“6. The machine learning system of claim 1, wherein the first data file is a two-dimensional image file, and the normalization procedure includes generating an input vector based on the image file two-dimensional.

A machine learning system according to claim 6, wherein the two-dimensional image file is selected from the group consisting of an x-ray image, a cat-scan (CT) image and a magnetic resonance (MRI) image.

“8. A machine learning system according to claim 1, wherein the first data file is a time varying real value parameter, and the normalization procedure produces an input vector based on the varying real value parameter in time.

The machine learning system of claim 8, wherein the time-varying real value parameter is a heartbeat audio file.

10. A machine learning system according to claim 8, wherein the actual time-varying parameter is a spoken utterance.

“11. The machine learning system of claim 1, wherein the first data file is a text file, and the normalization procedure includes producing an input vector by applying natural language processing (NLP) to the text file.

The machine learning system of claim 1, wherein the prediction output is further processed to determine a selected health care provider for the selected medical intervention.

“13. A machine learning system according to claim 1, wherein the data sources are selected from the group consisting of sources of diagnostic images, radiology reports, laboratory studies, examination results, survey results and office notes.

“14. A method for determining the appropriateness of a selected medical intervention using a machine learning system, the method comprising: receiving, from a plurality of health-related data sources, at least one data file of a first type, and a second data file of a second type; performing a normalization procedure on at least one of the first and second data files; and applying at least one machine learning model previously trained to the normalized data files to produce a prediction output; wherein the prediction output includes a level of confidence associated with an adequacy of the selected medical intervention.

“15. The method of claim 14, wherein the at least one machine learning model is an artificial neural network.

“16. The method of claim 14, wherein the at least one machine learning model is a probabilistic neural network.

“17. The method of claim 14, wherein the at least one machine learning model is a convolutional neural network.

“18. The method of claim 14, wherein the at least one machine learning model is a decision tree.

A method according to claim 14, wherein the first data file is a two-dimensional image file, and the normalization procedure includes generating an input vector based on the two-dimensional image file.

“20. A method according to claim 19, wherein the two-dimensional image file is selected from the group comprising an x-ray image, a cat-scan (CT) image and a magnetic resonance image (MRI).

For more information on this patent application, see: Lieberman, Daniel M. Machine Learning Systems and Methods for Assessing Medical Interventions for Utilization Review. Classroom December 21, 2021 and posted April 14, 2022. Patent URL: https://appft.uspto.gov/netacgi/nph-Parser?Sect1=PTO1&Sect2=HITOFF&d=PG01&p=1&u=%2Fnetahtml%2FPTO%2Fsrchnum.html&r=1&f=G&l=50&s1=%2220220115135%22. PGNR .&OS=DN/20220115135&RS=DN/20220115135

(Our reports provide factual information on research and discoveries from around the world.)

Sherry J. Basler